MCP server providing automated, context-aware documentation and code convention insights for GitHub repos.
Key Features: Compact pre-edit repo context including conventions and gaps Change impact analysis linking code paths to docs and conventions Structured API endpoint context for touched code paths Agent memory system enabling AI agents to learn and recall long-term information with high accuracy.
Key Features: State-of-the-art long-term memory accuracy Supports multiple LLM providers (OpenAI, Anthropic, Gemini, etc.) Easy integration via LLM wrapper or direct API calls Persistent memory MCP server with knowledge graph, semantic search, cloud sync, and cross-session context management.
Key Features: Persistent storage with SQLite or cloud sync (S3, R2, D1) Hierarchical memory organization with sections and subsections Semantic search using TF-IDF, sentence-transformers, and OpenAI embeddings Provides up-to-date, version-specific code documentation and examples for libraries via CLI or MCP server.
Key Features: Version-specific documentation retrieval Supports CLI commands and MCP server integration Library ID resolution for precise doc fetching Local-first AI memory server storing knowledge as Markdown files with semantic search and optional cloud sync.
Key Features: Local-first plain text Markdown storage Two-way human and AI file editing Semantic knowledge graph with wikilinks Local privacy-first semantic and keyword search over PDFs, DOCX, Markdown, and text files with no external API needed.
Key Features: Runs entirely locally with no cloud dependencies Hybrid semantic and keyword search for improved accuracy Supports PDF, DOCX, Markdown, and plain text ingestion Local code intelligence engine indexing repos into a persistent knowledge graph with fast structural queries across 159 languages.
Key Features: Indexes 159 languages using tree-sitter and Hybrid LSP Supports 15 MCP tools including graph search, tracing, and impact analysis Runs as a single static native binary with zero dependencies Official DeepSeek MCP server for chat, completion, model listing, and balance endpoints.
MCP server to access and manage your Mendeley reference library and global catalog via API.
Key Features: Library document search and retrieval Folder and collection management Global catalog and DOI paper lookup Local memory layer indexing coding agent session histories for fast recall and cross-machine sync over SSH.
Key Features: Zero-dependency single binary, fully local operation Search 3.5 GB of session history in ~1.5 ms Supports multiple coding agents via MCP protocol Persistent memory server with hybrid search, knowledge graphs, context checkpoints, artifact storage, and personality context for AI agents.
Key Features: 17 tools for memory, knowledge graphs, context, and artifacts Hybrid BM25, vector, and graph search 24 relationship types for knowledge graphs Loads a personal profile mined from local AI coding session logs to make agents act like you.
Key Features: Local mining of session logs from Claude Code, Codex, Copilot CLI, OpenCode, and Google Antigravity Multi-layer profiles for different task categories Native loading in Claude Code and Codex agents